Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

My study notes and hands-on projects for CUDA-based GPU programming

NVIDIA DLA-SW, the recipes and tools for running deep learning workloads on NVIDIA DLA cores for inference applications.

CUDA Python: Performance meets Productivity

Finetuning BLOOM on a single GPU using gradient-accumulation

This code repository contains the code used for my "Optimizing Memory Usage for Training LLMs and Vision Transformers in PyTorch" blog post.

A collection of code snippets from the publication Daily Dose of Data Science on Substack: http://www.dailydoseofds.com/

A 120-day CUDA learning plan covering daily concepts, exercises, pitfalls, and references (including “Programming Massively Parallel Processors”). Features six capstone projects to solidify GPU par…

Some CUDA example code with READMEs.

NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

RAPIDS Deployment Documentation

cuML - RAPIDS Machine Learning Library

High-Performance FP32 GEMM on CUDA devices

collection of benchmarks to measure basic GPU capabilities

NVIDIA curated collection of educational resources related to general purpose GPU programming.

Accessing all private registers of a warp from main thread of warp.

Vietnamese CLIP using PhoBERT

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Apply GPU in ML and DL

NVIDIA Linux open GPU kernel module source

CUDA Templates and Python DSLs for High-Performance Linear Algebra

My first pygame

A CUDA tutorial to make people learn CUDA program from 0